Large multilingual language models such as mBERT or XLM-R enable zero-shot cross-lingual transfer in various IR and NLP tasks. Cao et al. (2020) proposed a data- and compute-efficient method for cross-lingual adjustment of mBERT that uses a small parallel corpus to make embeddings of related words across languages similar to each other. They showed it to be effective in NLI for five European languages. In contrast we experiment with a typologically diverse set of languages (Spanish, Russian, Vietnamese, and Hindi) and extend their original implementations to new tasks (XSR, NER, and QA) and an additional training regime (continual learning). Our study reproduced gains in NLI for four languages, showed improved NER, XSR, and cross-lingual QA results in three languages (though some cross-lingual QA gains were not statistically significant), while mono-lingual QA performance never improved and sometimes degraded. Analysis of distances between contextualized embeddings of related and unrelated words (across languages) showed that fine-tuning leads to "forgetting" some of the cross-lingual alignment information. Based on this observation, we further improved NLI performance using continual learning.
We study the effect of seven data augmentation (da) methods in factoid question answering, focusing on the biomedical domain, where obtaining training instances is particularly difficult. We experiment with data from the BioASQ challenge, which we augment with training instances obtained from an artificial biomedical machine reading comprehension dataset, or via back-translation, information retrieval, word substitution based on word2vec embeddings, or masked language modeling, question generation, or extending the given passage with additional context. We show that da can lead to very significant performance gains, even when using large pre-trained Transformers, contributing to a broader discussion of if/when da benefits large pre-trained models. One of the simplest da methods, word2vec-based word substitution, performed best and is recommended. We release our artificial training instances and code.
Multilingual pre-trained models are able to zero-shot transfer knowledge from rich-resource to low-resource languages in machine reading comprehension (MRC). However, inherent linguistic discrepancies in different languages could make answer spans predicted by zero-shot transfer violate syntactic constraints of the target language. In this paper, we propose a novel multilingual MRC framework equipped with a Siamese Semantic Disentanglement Model (SSDM) to disassociate semantics from syntax in representations learned by multilingual pre-trained models. To explicitly transfer only semantic knowledge to the target language, we propose two groups of losses tailored for semantic and syntactic encoding and disentanglement. Experimental results on three multilingual MRC datasets (i.e., XQuAD, MLQA, and TyDi QA) demonstrate the effectiveness of our proposed approach over models based on mBERT and XLM-100. Code is available at:https://github.com/wulinjuan/SSDM_MRC.
As a broad and major category in machine reading comprehension (MRC), the generalized goal of discriminative MRC is answer prediction from the given materials. However, the focuses of various discriminative MRC tasks may be diverse enough: multi-choice MRC requires model to highlight and integrate all potential critical evidence globally; while extractive MRC focuses on higher local boundary preciseness for answer extraction. Among previous works, there lacks a unified design with pertinence for the overall discriminative MRC tasks. To fill in above gap, we propose a lightweight POS-Enhanced Iterative Co-Attention Network (POI-Net) as the first attempt of unified modeling with pertinence, to handle diverse discriminative MRC tasks synchronously. Nearly without introducing more parameters, our lite unified design brings model significant improvement with both encoder and decoder components. The evaluation results on four discriminative MRC benchmarks consistently indicate the general effectiveness and applicability of our model, and the code is available at https://github.com/Yilin1111/poi-net.
Recent machine reading comprehension datasets such as ReClor and LogiQA require performing logical reasoning over text. Conventional neural models are insufficient for logical reasoning, while symbolic reasoners cannot directly apply to text. To meet the challenge, we present a neural-symbolic approach which, to predict an answer, passes messages over a graph representing logical relations between text units. It incorporates an adaptive logic graph network (AdaLoGN) which adaptively infers logical relations to extend the graph and, essentially, realizes mutual and iterative reinforcement between neural and symbolic reasoning. We also implement a novel subgraph-to-node message passing mechanism to enhance context-option interaction for answering multiple-choice questions. Our approach shows promising results on ReClor and LogiQA.
Evaluation metrics in machine learning are often hardly taken as loss functions, as they could be non-differentiable and non-decomposable, e.g., average precision and F1 score. This paper aims to address this problem by revisiting the surrogate loss learning, where a deep neural network is employed to approximate the evaluation metrics. Instead of pursuing an exact recovery of the evaluation metric through a deep neural network, we are reminded of the purpose of the existence of these evaluation metrics, which is to distinguish whether one model is better or worse than another. In this paper, we show that directly maintaining the relation of models between surrogate losses and metrics suffices, and propose a rank correlation-based optimization method to maximize this relation and learn surrogate losses. Compared to previous works, our method is much easier to optimize and enjoys significant efficiency and performance gains. Extensive experiments show that our method achieves improvements on various tasks including image classification and neural machine translation, and even outperforms state-of-the-art methods on human pose estimation and machine reading comprehension tasks. Code is available at: https://github.com/hunto/ReLoss.
Biomedical machine reading comprehension (biomedical-MRC) aims to comprehend complex biomedical narratives and assist healthcare professionals in retrieving information from them. The high performance of modern neural network-based MRC systems depends on high-quality, large-scale, human-annotated training datasets. In the biomedical domain, a crucial challenge in creating such datasets is the requirement for domain knowledge, inducing the scarcity of labeled data and the need for transfer learning from the labeled general-purpose (source) domain to the biomedical (target) domain. However, there is a discrepancy in marginal distributions between the general-purpose and biomedical domains due to the variances in topics. Therefore, direct-transferring of learned representations from a model trained on a general-purpose domain to the biomedical domain can hurt the model's performance. We present an adversarial learning-based domain adaptation framework for the biomedical machine reading comprehension task (BioADAPT-MRC), a neural network-based method to address the discrepancies in the marginal distributions between the general and biomedical domain datasets. BioADAPT-MRC relaxes the need for generating pseudo labels for training a well-performing biomedical-MRC model. We extensively evaluate the performance of BioADAPT-MRC by comparing it with the best existing methods on three widely used benchmark biomedical-MRC datasets -- BioASQ-7b, BioASQ-8b, and BioASQ-9b. Our results suggest that without using any synthetic or human-annotated data from the biomedical domain, BioADAPT-MRC can achieve state-of-the-art performance on these datasets. Availability: BioADAPT-MRC is freely available as an open-source project at \url{https://github.com/mmahbub/BioADAPT-MRC}.
Machine reading comprehension (MRC) of text data is one important task in Natural Language Understanding. It is a complex NLP problem with a lot of ongoing research fueled by the release of the Stanford Question Answering Dataset (SQuAD) and Conversational Question Answering (CoQA). It is considered to be an effort to teach computers how to "understand" a text, and then to be able to answer questions about it using deep learning. However, until now large-scale training on private text data and knowledge sharing has been missing for this NLP task. Hence, we present FedQAS, a privacy-preserving machine reading system capable of leveraging large-scale private data without the need to pool those datasets in a central location. The proposed approach combines transformer models and federated learning technologies. The system is developed using the FEDn framework and deployed as a proof-of-concept alliance initiative. FedQAS is flexible, language-agnostic, and allows intuitive participation and execution of local model training. In addition, we present the architecture and implementation of the system, as well as provide a reference evaluation based on the SQUAD dataset, to showcase how it overcomes data privacy issues and enables knowledge sharing between alliance members in a Federated learning setting.
Question Answering (QA) is a task in which a machine understands a given document and a question to find an answer. Despite impressive progress in the NLP area, QA is still a challenging problem, especially for non-English languages due to the lack of annotated datasets. In this paper, we present the Japanese Question Answering Dataset, JaQuAD, which is annotated by humans. JaQuAD consists of 39,696 extractive question-answer pairs on Japanese Wikipedia articles. We finetuned a baseline model which achieves 78.92% for F1 score and 63.38% for EM on test set. The dataset and our experiments are available at https://github.com/SkelterLabsInc/JaQuAD.
We target the task of cross-lingual Machine Reading Comprehension (MRC) in the direct zero-shot setting, by incorporating syntactic features from Universal Dependencies (UD), and the key features we use are the syntactic relations within each sentence. While previous work has demonstrated effective syntax-guided MRC models, we propose to adopt the inter-sentence syntactic relations, in addition to the rudimentary intra-sentence relations, to further utilize the syntactic dependencies in the multi-sentence input of the MRC task. In our approach, we build the Inter-Sentence Dependency Graph (ISDG) connecting dependency trees to form global syntactic relations across sentences. We then propose the ISDG encoder that encodes the global dependency graph, addressing the inter-sentence relations via both one-hop and multi-hop dependency paths explicitly. Experiments on three multilingual MRC datasets (XQuAD, MLQA, TyDiQA-GoldP) show that our encoder that is only trained on English is able to improve the zero-shot performance on all 14 test sets covering 8 languages, with up to 3.8 F1 / 5.2 EM improvement on-average, and 5.2 F1 / 11.2 EM on certain languages. Further analysis shows the improvement can be attributed to the attention on the cross-linguistically consistent syntactic path.
Scientific claim verification can help the researchers to easily find the target scientific papers with the sentence evidence from a large corpus for the given claim. Some existing works propose pipeline models on the three tasks of abstract retrieval, rationale selection and stance prediction. Such works have the problems of error propagation among the modules in the pipeline and lack of sharing valuable information among modules. We thus propose an approach, named as ARSJoint, that jointly learns the modules for the three tasks with a machine reading comprehension framework by including claim information. In addition, we enhance the information exchanges and constraints among tasks by proposing a regularization term between the sentence attention scores of abstract retrieval and the estimated outputs of rational selection. The experimental results on the benchmark dataset SciFact show that our approach outperforms the existing works.
We study the robustness of machine reading comprehension (MRC) models to entity renaming -- do models make more wrong predictions when the same questions are asked about an entity whose name has been changed? Such failures imply that models overly rely on entity information to answer questions, and thus may generalize poorly when facts about the world change or questions are asked about novel entities. To systematically audit this issue, we present a pipeline to automatically generate test examples at scale, by replacing entity names in the original test sample with names from a variety of sources, ranging from names in the same test set, to common names in life, to arbitrary strings. Across five datasets and three pretrained model architectures, MRC models consistently perform worse when entities are renamed, with particularly large accuracy drops on datasets constructed via distant supervision. We also find large differences between models: SpanBERT, which is pretrained with span-level masking, is more robust than RoBERTa, despite having similar accuracy on unperturbed test data. We further experiment with different masking strategies as the continual pretraining objective and find that entity-based masking can improve the robustness of MRC models.
Machine reading comprehension is a heavily-studied research and test field for evaluating new pre-trained language models (PrLMs) and fine-tuning strategies, and recent studies have enriched the pre-trained language models with syntactic, semantic and other linguistic information to improve the performance of the models. In this paper, we imitate the human reading process in connecting the anaphoric expressions and explicitly leverage the coreference information of the entities to enhance the word embeddings from the pre-trained language model, in order to highlight the coreference mentions of the entities that must be identified for coreference-intensive question answering in QUOREF, a relatively new dataset that is specifically designed to evaluate the coreference-related performance of a model. We use two strategies to fine-tune a pre-trained language model, namely, placing an additional encoder layer after a pre-trained language model to focus on the coreference mentions or constructing a relational graph convolutional network to model the coreference relations. We demonstrate that the explicit incorporation of coreference information in the fine-tuning stage performs better than the incorporation of the coreference information in pre-training a language model.
Multi-party dialogue machine reading comprehension (MRC) raises an even more challenging understanding goal on dialogue with more than two involved speakers, compared with the traditional plain passage style MRC. To accurately perform the question-answering (QA) task according to such multi-party dialogue, models have to handle fundamentally different discourse relationships from common non-dialogue plain text, where discourse relations are supposed to connect two far apart utterances in a linguistics-motivated way.To further explore the role of such unusual discourse structure on the correlated QA task in terms of MRC, we propose the first multi-task model for jointly performing QA and discourse parsing (DP) on the multi-party dialogue MRC task. Our proposed model is evaluated on the latest benchmark Molweni, whose results indicate that training with complementary tasks indeed benefits not only QA task, but also DP task itself. We further find that the joint model is distinctly stronger when handling longer dialogues which again verifies the necessity of DP in the related MRC.
Recent work has shown that feed-forward networks (FFNs) in pre-trained Transformers are a key component, storing various linguistic and factual knowledge. However, the computational patterns of FFNs are still unclear. In this work, we study the computational patterns of FFNs and observe that most inputs only activate a tiny ratio of neurons of FFNs. This phenomenon is similar to the sparsity of the human brain, which drives research on functional partitions of the human brain. To verify whether functional partitions also emerge in FFNs, we propose to convert a model into its MoE version with the same parameters, namely MoEfication. Specifically, MoEfication consists of two phases: (1) splitting the parameters of FFNs into multiple functional partitions as experts, and (2) building expert routers to decide which experts will be used for each input. Experimental results show that MoEfication can conditionally use 10% to 30% of FFN parameters while maintaining over 95% original performance for different models on various downstream tasks. Besides, MoEfication brings two advantages: (1) it significantly reduces the FLOPS of inference, i.e., 2x speedup with 25% of FFN parameters, and (2) it provides a fine-grained perspective to study the inner mechanism of FFNs. The source code of this paper can be obtained from https://github.com/thunlp/MoEfication.
We propose MultiDoc2Dial, a new task and dataset on modeling goal-oriented dialogues grounded in multiple documents. Most previous works treat document-grounded dialogue modeling as a machine reading comprehension task based on a single given document or passage. In this work, we aim to address more realistic scenarios where a goal-oriented information-seeking conversation involves multiple topics, and hence is grounded on different documents. To facilitate such a task, we introduce a new dataset that contains dialogues grounded in multiple documents from four different domains. We also explore modeling the dialogue-based and document-based context in the dataset. We present strong baseline approaches and various experimental results, aiming to support further research efforts on such a task.
We propose CodeQA, a free-form question answering dataset for the purpose of source code comprehension: given a code snippet and a question, a textual answer is required to be generated. CodeQA contains a Java dataset with 119,778 question-answer pairs and a Python dataset with 70,085 question-answer pairs. To obtain natural and faithful questions and answers, we implement syntactic rules and semantic analysis to transform code comments into question-answer pairs. We present the construction process and conduct systematic analysis of our dataset. Experiment results achieved by several neural baselines on our dataset are shown and discussed. While research on question-answering and machine reading comprehension develops rapidly, few prior work has drawn attention to code question answering. This new dataset can serve as a useful research benchmark for source code comprehension.
Named Entity Recognition (NER) has seen significant progress in recent years, with numerous state-of-the-art (SOTA) models achieving high performance. However, very few studies have focused on the generation of entities' context. In this paper, we introduce CONTEXT-NER, a task that aims to generate the relevant context for entities in a sentence, where the context is a phrase describing the entity but not necessarily present in the sentence. To facilitate research in this task, we also present the EDGAR10-Q dataset, which consists of annual and quarterly reports from the top 1500 publicly traded companies. The dataset is the largest of its kind, containing 1M sentences, 2.8M entities, and an average of 35 tokens per sentence, making it a challenging dataset. We propose a baseline approach that combines a phrase generation algorithm with inferencing using a 220M language model, achieving a ROUGE-L score of 27% on the test split. Additionally, we perform a one-shot inference with ChatGPT, which obtains a 30% ROUGE-L, highlighting the difficulty of the dataset. We also evaluate models such as T5 and BART, which achieve a maximum ROUGE-L of 49% after supervised finetuning on EDGAR10-Q. We also find that T5-large, when pre-finetuned on EDGAR10-Q, achieve SOTA results on downstream finance tasks such as Headline, FPB, and FiQA SA, outperforming vanilla version by 10.81 points. To our surprise, this 66x smaller pre-finetuned model also surpasses the finance-specific LLM BloombergGPT-50B by 15 points. We hope that our dataset and generated artifacts will encourage further research in this direction, leading to the development of more sophisticated language models for financial text analysis
Semantic Role Labeling (SRL) aims at recognizing the predicate-argument structure of a sentence and can be decomposed into two subtasks: predicate disambiguation and argument labeling. Prior work deals with these two tasks independently, which ignores the semantic connection between the two tasks. In this paper, we propose to use the machine reading comprehension (MRC) framework to bridge this gap. We formalize predicate disambiguation as multiple-choice machine reading comprehension, where the descriptions of candidate senses of a given predicate are used as options to select the correct sense. The chosen predicate sense is then used to determine the semantic roles for that predicate, and these semantic roles are used to construct the query for another MRC model for argument labeling. In this way, we are able to leverage both the predicate semantics and the semantic role semantics for argument labeling. We also propose to select a subset of all the possible semantic roles for computational efficiency. Experiments show that the proposed framework achieves state-of-the-art or comparable results to previous work. Code is available at \url{https://github.com/ShannonAI/MRC-SRL}.
Transformer-based pre-trained models, such as BERT, have achieved remarkable results on machine reading comprehension. However, due to the constraint of encoding length (e.g., 512 WordPiece tokens), a long document is usually split into multiple chunks that are independently read. It results in the reading field being limited to individual chunks without information collaboration for long document machine reading comprehension. To address this problem, we propose RoR, a read-over-read method, which expands the reading field from chunk to document. Specifically, RoR includes a chunk reader and a document reader. The former first predicts a set of regional answers for each chunk, which are then compacted into a highly-condensed version of the original document, guaranteeing to be encoded once. The latter further predicts the global answers from this condensed document. Eventually, a voting strategy is utilized to aggregate and rerank the regional and global answers for final prediction. Extensive experiments on two benchmarks QuAC and TriviaQA demonstrate the effectiveness of RoR for long document reading. Notably, RoR ranks 1st place on the QuAC leaderboard (https://quac.ai/) at the time of submission (May 17th, 2021).